AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Learning Overcomplete HMMs

Vatsal Sharan, Sham M. Kakade, Percy Liang, Gregory Valiant

NeurIPS 2017 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse regression with guarantees · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use tensor-decomposition method of moments under sparse, well-conditioned transitions with few short cycles and random small-support outputsOvercomplete HMMs · HMMs satisfying the stated assumptionssample complexity: \poly{n,1/\epsilon}Improved
Use a transition support containing a permutation whose cycles are at least 2⌈log_m n⌉ statesSparse HMMs · Sparse HMM identifiabilityidentifiability window length: 4\lceil \log_m n\rceil +1Improved
Use a window length of 2⌈log_m n⌉ + 1 for generic HMMsGeneric HMMs · Generic HMM identifiabilityidentifiability window length: 2\lceil \log_m n\rceil +1Improved
Increase the probability mass on short cyclesTransition matrix and likelihood matrix A · Simulation with n=128conditioning of likelihood matrix AHurt
Increase transition degree or probability mass on the dense transition componentTransition matrix and likelihood matrix A · Simulation with n=128conditioning of likelihood matrix AHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy